embedUR systems develops edge AI solution on NXP platform to advance automotive sensing technology
embedUR systems has developed an Ultra-Wideband (UWB) Sensing Edge AI solution with NXP® Semiconductor’s Trimension™ NCJ29D6 platform. This technology powers gesture-based control, such as hands-free trunk opening for cars, and extends to advanced sensing applications in automotive and beyond.
NXP’s Trimension NCJ29D6 is a fully integrated, low-energy UWB transceiver IC designed for secure ranging and radar applications in automotive environments. It supports Digital Key functionality for seamless, hands-free vehicle access while also enabling radar-based applications, such as Child Presence Detection (CPD) and kick-sensing for easy trunk access. By leveraging ranging and radar capabilities in a single chip, the Trimension NCJ29D6 maximises system value and reduces overall cost.
embedUR systems optimised a lightweight and efficient UWB Gesture and Motion Recognition Model to work with NXP’s Trimension NCJ29D6, allowing for real-time gesture detection at a compact model size of just 215 KB.
Enhancing Experiences with UWB AI
This UWB-powered AI model allows for intuitive, touch-free vehicle interactions, and enables new affordable opportunities all running on the Edge, such as:
⦁ Touch-Free Trunk Opening – Open the trunk with a wave of a hand or foot.
⦁ Parking Assistance – Start/stop automated parking maneuvers using gestures.
Beyond automotive, this technology can be adapted for consumer electronics, industrial automation, and smart home applications, enabling touch-free user interactions across multiple industries.
Optimised AI for UWB Sensing Applications
embedUR systems specialises in embedded AI on the Edge, model optimisation, and real-time processing on power-efficient, low-memory edge devices. The combination of secure ranging and radar support in the Trimension NCJ29D6 provides a unique foundation for advanced AI-driven sensing applications. By leveraging this platform, embedUR delivers robust and efficient UWB gesture recognition for a range of use cases.
“With our expertise in embedded AI and UWB technology, we are delivering practical, hands-free interaction solutions that enhance safety and convenience,” said Eric Smiley, VP of Business Development at embedUR systems. “This project demonstrates how UWB, combined with optimised Edge AI models, can help create advanced sensing applications for automotive and beyond.”
Michael Leitner, General Manager, Secure Car Access at NXP Semiconductors, confirms: “The knowledge of embedUR in wireless sensing and efficient implementation of data processing on edge devices positions embedUR to fully leverage the capabilities of our Ultra-Wideband (UWB) devices. EmbedUR demonstrated very positive results in UWB-based gesture sensing and we are looking forward to further applications that embedUR is able to address based on our UWB IC.”
Driving Edge AI Acceleration
With over two decades of expertise in embedded systems and wireless technologies, embedUR has delivered AI-powered solutions across automotive, industrial, and IoT markets. embedUR has developed a range of Edge AI applications, such as a real-time image segmentation model running on an Arm® Cortex®-M7 at under 300 KB and deployed facial recognition AI pipelines on a low-power edge device with <1MB memory footprints. embedUR’s engineers routinely optimise AI models to fit within 200–500 KB, enabling real-time inference on power and memory efficient platforms without sacrificing accuracy. This proven track record in model compression, quantisation, and efficient runtime integration positions embedUR to help customers accelerate development cycles, meet strict power/memory budgets, and bring next-generation products to market faster.
